Skip to content
Database ⇄ AI

Azure Cosmos DB to Azure OpenAI integration — real-time data sync

Keep Azure Cosmos DB and Azure OpenAI in sync without custom scripts. Cut weeks of integration work, eliminate silent data drift, and give your team a single, reliable source of truth.

  • SOC 2 and 6 other compliance frameworks
  • POC with real engineers in minutes

Adopted by fast-scaling companies moving mission-critical data in real time

Case study
Migrated from MuleSoft
Case study
Migrated from Celigo
Migrated from Heroku Connect
Migrated from Matillion
Case study
Migrated from Fivetran
Case study
Migrated from Celigo
Why teams connect Azure Cosmos DB and Azure OpenAI

Sync the records in Azure Cosmos DB into Azure OpenAI and land its embeddings, classifications, and generated fields back on the same rows, in real time and without a pipeline to maintain.

Azure OpenAI is a read-only source: Stacksync reads its data in real time and delivers it into Azure Cosmos DB, so Azure Cosmos DB always reflects the current state of Azure OpenAI — without exports, scripts, or schedulers.

AI systems do not hold customers or invoices the way business apps do. What they hold is derived from your data: the vectors and metadata in a vector store, or the classifications, extracted fields, and generated text a model produces over records it was given. Azure Cosmos DB is where those source records actually live. The bridge between the two is the row itself, since an item in Azure OpenAI and the record in Azure Cosmos DB it describes are two halves of the same thing, and they drift the moment one is updated without the other.

Stacksync syncs Partition keys, Change feed entries, Stored procedures and triggers, Databases in Azure Cosmos DB with Usage and quota, Assistants, Vector stores, Deployments in Azure OpenAI in real time. Rows created or changed in Azure Cosmos DB flow into Azure OpenAI so inference and embedding run on current data, and the scores, labels, and generated fields Azure OpenAI produces flow back onto the matching rows in Azure Cosmos DB, mapped field by field. A change on either side appears on the other within seconds, with no extraction job or webhook plumbing to keep alive.

Because matching is by a stable identifier, every row in Azure Cosmos DB stays tied to its AI-side counterpart in Azure OpenAI. Retrieval, enrichment, and generated content always resolve back to the record they came from, so there are no orphaned vectors and no labels describing a version of a row that no longer exists.

Common use cases

  • 01 Pull per-deployment TPM/RPM usage into a warehouse for FinOps chargeback and quota-exhaustion alerting.
  • 02 Mirror Assistants and Vector stores configuration into a database as an auditable inventory of retrieval assets and their linked files.
  • 03 Consolidate documents from multiple containers into a single reporting store.
  • 04 Stream operational documents from Cosmos DB into a SQL warehouse via the change feed for analytics without hitting request-unit budgets with full scans.

Common sync patterns

One record, one identifier

Each item in Azure OpenAI carries the key of the row in Azure Cosmos DB it came from, so results resolve back to the exact record with nothing orphaned or duplicated.

Run the AI on current data

Rows created or changed in Azure Cosmos DB flow into Azure OpenAI as they happen, so embeddings, classifications, and prompts run on the latest records instead of a nightly snapshot.

Write results back onto the record

Scores, labels, extracted fields, or generated text produced in Azure OpenAI land on the matching row in Azure Cosmos DB, next to the source data your applications already query.

What you can sync between Azure Cosmos DB and Azure OpenAI

Representative objects on each side — any object or custom field can map to any target. Schemas are auto-detected; types are converted between the two systems.

Azure Cosmos DB objects Azure OpenAI objects How this pairing syncs
Partition keys Determine data distribution and must be included on writes for the sync to route items correctly. Usage and quota Per-deployment TPM/RPM consumption and remaining quota, read from usage endpoints and Azure Monitor for cost and throttling reporting. Partition keys is specific to Azure Cosmos DB and Usage and quota to Azure OpenAI — each maps to any object or custom field on the other side.
Change feed entries Ordered record of inserts and updates per partition, consumed for incremental sync. Assistants Persistent assistants (preview) with instructions, tools, and linked files; read as configuration inventory, not authored via sync. Change feed entries is specific to Azure Cosmos DB and Assistants to Azure OpenAI — each maps to any object or custom field on the other side.
Stored procedures and triggers Server-side logic scoped to a partition; relevant when writes must respect existing validation. Vector stores File collections (preview) backing file-search retrieval; read as metadata such as name, file counts, and status. Stored procedures and triggers is specific to Azure Cosmos DB and Vector stores to Azure OpenAI — each maps to any object or custom field on the other side.
Databases Top-level namespaces that scope containers and throughput provisioning. Deployments Named model deployments (model, version, SKU, assigned TPM capacity) read as a control-plane inventory via Azure Resource Manager; read-only in sync. Databases is specific to Azure Cosmos DB and Deployments to Azure OpenAI — each maps to any object or custom field on the other side.
Containers The unit of partitioning and throughput; each container maps to a synced collection. Models Catalog of base and fine-tunable models available per region; read-only reference data used to resolve deployment and fine-tuning targets. Containers is specific to Azure Cosmos DB and Models to Azure OpenAI — each maps to any object or custom field on the other side.
Items (JSON documents) Schema-flexible JSON records read and written during sync; nested structures are flattened or mapped as needed. Fine-tuning jobs Training jobs with status, base model, hyperparameters, and result files; status is polled from queued through succeeded or failed. Items (JSON documents) is specific to Azure Cosmos DB and Fine-tuning jobs to Azure OpenAI — each maps to any object or custom field on the other side.

How changes propagate between Azure Cosmos DB and Azure OpenAI

Each direction of the sync is driven by what the source system can signal and what the destination accepts — detection, delivery, and expected latency below.

Azure Cosmos DB Azure OpenAI Sub-second propagation

DetectionChanges in Azure Cosmos DB are captured at the source via change data capture — no polling loop against its API. Built-in change feed exposing inserts and updates in order within each partition key range.

DeliveryAzure OpenAI does not accept inbound record writes, so this direction carries requests rather than records: Azure OpenAI's output flows back as field updates on the originating Azure Cosmos DB records.

Azure OpenAI Azure Cosmos DB Interval-based propagation

DetectionStacksync polls Azure OpenAI for changes on an incremental schedule, reading only records changed since the previous pass. Polling: list endpoints plus GET on job IDs for status.

DeliveryEach detected change is applied to Azure Cosmos DB as a row-level write, with types converted between the two schemas.

Rate-limit considerations

  • Azure OpenAI: Per-deployment TPM and RPM limits (about 6 RPM per 1000 TPM), scoped by region and subscription; control-plane ARM calls throttle separately.
What ships with Azure Cosmos DB ⇄ Azure OpenAI

Connect Azure Cosmos DB and Azure OpenAI for flexible, real-time data sync.

Real-time sync, workflow automation, event queues, EDI, and monitoring, for every Azure Cosmos DB–Azure OpenAI connection.

Real-time

Real-time sync

Changes in Azure Cosmos DB or Azure OpenAI instantly reflect in both systems. No stale data, no manual imports.

No-code + pro-code

Workflow automation

Trigger automated workflows whenever Azure Cosmos DB or Azure OpenAI data changes, update records, fire webhooks, or kick off sequences without brittle API scripts.

At scale

Event queues

Handle millions of events per minute without losing a single Azure Cosmos DB or Azure OpenAI record.

Observability

Monitoring

Track your Azure Cosmos DB ⇄ Azure OpenAI sync health, view errors, and replay failed events in one click.

Trading partners

EDI

Transform legacy EDI complexity into simple database interactions between Azure Cosmos DB and Azure OpenAI.

How the Azure Cosmos DB and Azure OpenAI connectors work

Azure Cosmos DB

Integration surface
REST API and SDKs over HTTPS (API for NoSQL, formerly the SQL API); also MongoDB, Cassandra, Gremlin, and Table API surfaces
Authentication
Account keys, resource tokens, or Microsoft Entra ID role-based access
Change detection
Built-in change feed exposing inserts and updates in order within each partition key range
Capabilities
read · write · CDC

Azure OpenAI

Integration surface
REST data-plane (inference + authoring) and Azure Resource Manager control-plane
Authentication
API key in the api-key header, or a Microsoft Entra ID bearer token / managed identity
Change detection
Polling: list endpoints plus GET on job IDs for status; no webhooks or change feed. Fine-tuning and batch jobs expose queued/running/succeeded states.
Capabilities
read
Rate limits
Per-deployment TPM and RPM limits (about 6 RPM per 1000 TPM), scoped by region and subscription; control-plane ARM calls throttle separately.
How it works

How to connect Azure Cosmos DB to Azure OpenAI — three steps, no code

Configure and sync within minutes, no code. Whether you sync 50k or 100M+ records, Stacksync handles the queues, infra, and plumbing. Integrations are non-invasive and need zero setup on your systems.

  1. 01

    Connect your apps

    Authenticate Azure Cosmos DB and Azure OpenAI with each platform's native method — OAuth, API keys, or service accounts — plus secure options like SSH tunneling, IP whitelisting, and VPC peering.

    • OAuth 2.0
    • SSH tunnel
    • VPC peering
    Azure Cosmos DB connected
    Azure OpenAI connected
    OAuth 2.0
    SSH tunnel
    SSL certificate
    VPC peering
  2. 02

    Choose tables

    Pick the Azure Cosmos DB and Azure OpenAI objects to sync — Stacksync auto-detects both schemas, including custom fields where the platform exposes them. Sync to existing tables, or let Stacksync create new ones with ideal data types.

    • Standard objects
    • Custom objects
    • Auto-schema
    objects · Azure Cosmos DB ⇄ Azure OpenAI
    Customers 12,480
    Sales Orders 8,213
    Invoices 5,902
    Items 1,344
  3. 03

    Map fields

    Fields map automatically even when names and types differ. Stacksync handles transformation and type casting for you, zero configuration required.

    • Auto-map
    • Type casting
    • Transforms
    Azure Cosmos DB Azure OpenAI
    Company company_name text
    Email email text
    Amount amount numeric
    Created created_at timestamp
Try interactive demo
FAQ

Azure Cosmos DB and Azure OpenAI integration FAQ

SECURITY

Security teams trust Stacksync

As a data company, we understand the importance of keeping your data secure. Stacksync is built with security best practices to keep your data safe at every layer, and is DPF-certified for US, EU, UK and CH data transfers.

Learn more about security
SOC 2 Type II
ISO 27001
HIPAA BAA
GDPR
CCPA
DPF US-EU-UK-CH
→ SECURITY WITH BENEFITS

SSO & SCIM

Let your users access Stacksync from your centralized user management systems. Works with Okta, Azure, Google SSO and more.

Alerts

Immediately get alerted about record syncing issues over email, Slack, PagerDuty and WhatsApp. Resolve issues from a centralized dashboard with retry and revert options.

Secure connection options

Securely connects to your systems with:

OAuth 2 SSH Tunnelling SSL certificates IP Whitelisting VPN gateway VPC peering and more

Related integrations

Every pair below is a real-time, two-way sync. Search all 411 integrations available for Azure Cosmos DB and Azure OpenAI.

Popular · 7 of 411
All Azure Cosmos DB integrations All Azure OpenAI integrations Browse all integrations
Coworkers laughing in front of a laptop in a casual office setting

Your last integration took months.
Your next one takes a prompt.

Book a demo Tour the platform on your own